Gemma 3 4B Pt — Hardware Requirements & GPU Compatibility
Vision
Gemma 3 4B PT is Google's pretrained checkpoint at the small end of the Gemma 3 family, with about 4.3 billion parameters including its vision components. It uses a vision-language architecture that accepts text and images. The PT suffix marks the base model: it is not instruction-tuned and does not follow chat prompts reliably, so it is meant for fine-tuning, research and experimentation rather than direct use as an assistant. At this size it runs on almost any recent GPU or even a CPU once quantized, with the instruction-tuned release the better pick for conversation. Like the larger Gemma 3 models, it supports a 128K-token context window. It is distributed under the Gemma Terms of Use, and access requires acknowledging the license on Hugging Face. Published in February 2025, it is one of the smaller pretrained models in the Gemma 3 lineup alongside the 12B and 27B sizes.
120.0K downloads
171 likesSpecifications
- Publisher
- Family
- Gemma 3
- Parameters
- 4.3B
- Release Date
- 2025-02-20
- License
- Gemma Terms
Get Started
HuggingFace
How Much VRAM Does Gemma 3 4B Pt Need?
Select a quantization to see compatible GPUs below.
| Quantization | Bits | VRAM | + Context | File Size | Quality |
|---|---|---|---|---|---|
| Q2_K | 3.40 | 2.0 GB | — | 1.83 GB | 2-bit quantization with K-quant improvements |
| Q3_K_S | 3.50 | 2.1 GB | — | 1.88 GB | 3-bit small quantization |
| Q3_K_M | 3.90 | 2.3 GB | — | 2.10 GB | 3-bit medium quantization |
| Q4_0 | 4.00 | 2.4 GB | — | 2.15 GB | 4-bit legacy quantization |
| Q4_K_M | 4.80 | 2.8 GB | — | 2.58 GB | 4-bit medium quantization — most popular sweet spot |
| Q5_K_M | 5.70 | 3.4 GB | — | 3.06 GB | 5-bit medium quantization — good quality/size tradeoff |
| Q6_K | 6.60 | 3.9 GB | — | 3.55 GB | 6-bit quantization, very good quality |
| Q8_0 | 8.00 | 4.7 GB | — | 4.30 GB | 8-bit quantization, near-lossless |
est.= calculated VRAM estimate; no published GGUF file found for that quantization yet. Other rows are verified against real community uploads.
Which GPUs Can Run Gemma 3 4B Pt?
Q4_K_M · 2.8 GBGemma 3 4B Pt (Q4_K_M) requires 2.8 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 4+ GB is recommended. 52 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti.
Runs great
— Plenty of headroomWhich Devices Can Run Gemma 3 4B Pt?
Q4_K_M · 2.8 GB59 devices with unified memory can run Gemma 3 4B Pt, including NVIDIA DGX H100, NVIDIA DGX A100 640GB.
Runs great
— Plenty of headroomWhere to Download Gemma 3 4B Pt
Community quantizations of this model — GGUF for llama.cpp, Ollama, and LM Studio, plus AWQ/MLX variants where available.
Related Models
Frequently Asked Questions
- How much VRAM does Gemma 3 4B Pt need?
Gemma 3 4B Pt requires 2.8 GB of VRAM at Q4_K_M, or 9.5 GB at BF16.
VRAM = Weights + KV Cache + Overhead
Weights = 4.3B × 4.8 bits ÷ 8 = 2.6 GB
KV Cache + Overhead ≈ 0.2 GB (at 2K context + ~0.3 GB framework)
VRAM usage by quantization
Q4_K_M2.8 GB- What's the best quantization for Gemma 3 4B Pt?
For Gemma 3 4B Pt, Q4_K_M (2.8 GB) offers the best balance of quality and VRAM usage. Q5_K_S (3.3 GB) provides better quality if you have the VRAM. The smallest option is Q2_K at 2.0 GB.
VRAM requirement by quantization
Q2_K2.0 GBQ4_02.4 GBQ4_K_S2.7 GBQ4_K_M ★2.8 GBQ5_K_M3.4 GBBF169.5 GB★ Recommended — best balance of quality and VRAM usage.
- Can I run Gemma 3 4B Pt on a Mac?
Gemma 3 4B Pt requires at least 2.0 GB at Q2_K, which exceeds the unified memory of most consumer Macs. You would need a Mac Studio or Mac Pro with a high-memory configuration.
- Can I run Gemma 3 4B Pt locally?
Yes — Gemma 3 4B Pt can run locally on consumer hardware. At Q4_K_M quantization it needs 2.8 GB of VRAM. Popular tools include Ollama, LM Studio, and llama.cpp.
- How fast is Gemma 3 4B Pt?
At Q4_K_M, Gemma 3 4B Pt can reach ~1690 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~231 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 2.8 × 0.65 = ~1831 tok/s
Estimated speed at Q4_K_M (2.8 GB)
~1831 tok/s~231 tok/s~1831 tok/s~1690 tok/sReal-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
- What's the download size of Gemma 3 4B Pt?
At Q4_K_M, the download is about 2.58 GB. The full-precision BF16 version is 8.60 GB. The smallest option (Q2_K) is 1.83 GB.
- Which GPUs can run Gemma 3 4B Pt?
52 consumer GPUs can run Gemma 3 4B Pt at Q4_K_M (2.8 GB). Top options include AMD Radeon RX 6700 XT, AMD Radeon RX 6800, AMD Radeon RX 6800 XT. 52 GPUs have plenty of headroom for comfortable inference.
- Which devices can run Gemma 3 4B Pt?
59 devices with unified memory can run Gemma 3 4B Pt at Q4_K_M (2.8 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Apple iPhone 17 Pro, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.